cyberbabooshka/uae_large_ft1

SentenceTransformer based on WhereIsAI/UAE-Large-V1

This is a sentence-transformers model finetuned from WhereIsAI/UAE-Large-V1. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: WhereIsAI/UAE-Large-V1
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("cyberbabooshka/uae_large_ft1")
# Run inference
sentences = [
    'What is the relationship between the smallest perturbation of a matrix and its rank, as established in theorems regarding matrix perturbations?',
    '"Suppose $A \\in C^{m \\times n}$ has full column rank (= n). Then $\\min _{\\Delta \\in \\mathbb{C}^{m \\times n}}\\left\\{\\|\\Delta\\|_{2} \\mid A+\\Delta \\text { has rank }<n\\right\\}=\\sigma_{n}(A)$."',
    '"If a beam of light enters and then exits the elevator, the observer on Earth and the one accelerating in empty space must observe the same thing, since they cannot distinguish between being on Earth or accelerating in space. The observer in space, who is accelerating, will observe that the beam of light bends as it crosses the elevator... that means that if the path of a beam of light is curved near Earth, it must be because space itself is curved in the presence of a gravitational field!"',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

• Dataset: eval
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6143
cosine_accuracy@3	0.7357
cosine_accuracy@5	0.7833
cosine_accuracy@10	0.8381
cosine_precision@1	0.6143
cosine_precision@3	0.2452
cosine_precision@5	0.1567
cosine_precision@10	0.0838
cosine_recall@1	0.6143
cosine_recall@3	0.7357
cosine_recall@5	0.7833
cosine_recall@10	0.8381
cosine_ndcg@10	0.7235
cosine_mrr@10	0.6871
cosine_map@100	0.6925

Training Details

Training Dataset

Unnamed Dataset

• Size: 1,760 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 9 tokens mean: 24.87 tokens max: 70 tokens	min: 11 tokens mean: 68.37 tokens max: 500 tokens

• Samples:

  anchor	positive
  How is a proper coloring of a graph defined in the context of vertices and edges?	"A coloring is called proper if for each edge joining two distinct vertices, the two vertices it joins have different colors."
  What is the relationship between the first excited state of the box model and the p orbitals in a hydrogen atom?	"The p orbitals are similar to the first excited state of the box, i.e. $(n_{x},n_{y},n_{z})=(2,1,1)$ is similar to a $p_{x}$ orbital, $(n_{x},n_{y},n_{z})=(1,2,1)$ is similar to a $p_{y}$ orbital and $(n_{x},n_{y},n_{z})=(1,1,2)$ is similar to a $p_{z}$ orbital."
  How can the behavior of the derivative ( f'(x) ) indicate the presence of a local maximum or minimum at a critical point ( x=a )?	"If there is a local maximum when ( x=a ), the function must be lower near ( x=a ) than it is right at ( x=a ). If the derivative exists near ( x=a ), this means ( f'(x)>0 ) when ( x ) is near ( a ) and ( x < a ), because the function must 'slope up' just to the left of ( a ). Similarly, ( f'(x) < 0 ) when ( x ) is near ( a ) and ( x>a ), because ( f ) slopes down from the local maximum as we move to the right. Using the same reasoning, if there is a local minimum at ( x=a ), the derivative of ( f ) must be negative just to the left of ( a ) and positive just to the right."

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 420 evaluation samples
• Columns: anchor and positive
• Approximate statistics based on the first 420 samples:

  	anchor	positive
  type	string	string
  details	min: 12 tokens mean: 24.97 tokens max: 66 tokens	min: 7 tokens mean: 68.52 tokens max: 452 tokens

• Samples:

  anchor	positive
  What are the two central classes mentioned in the FileSystem framework and what do they represent?	"The class FileReference is the most important entry point to the framework." and "FileSystem is a powerful and elegant library to manipulate files."
  What is the significance of Turing's work in the context of PDE-based models for self-organization of complex systems?	"Turing’s monumental work on the chemical basis of morphogenesis played an important role in igniting researchers’ attention to the PDE-based continuous field models as a mathematical framework to study self-organization of complex systems."
  What are the two options for reducing accelerations as discussed in the passage?	"From the above definitions we see that there are really two options for reducing accelerations. We can reduce the amount that velocity changes, or we can increase the time over which the velocity changes (or both)."

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• learning_rate: 2e-05
• weight_decay: 0.05
• num_train_epochs: 10
• warmup_ratio: 0.1
• fp16: True
• eval_on_start: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 2e-05
• weight_decay: 0.05
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 10
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: False
• fp16: True
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: True
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss	eval_cosine_ndcg@10
0	0	-	0.0971	0.6824
0.0091	1	0.1198	-	-
0.0182	2	0.0787	-	-
0.0273	3	0.0614	-	-
0.0364	4	0.138	-	-
0.0455	5	0.1204	-	-
0.0545	6	0.1885	-	-
0.0636	7	0.0475	-	-
0.0727	8	0.1358	-	-
0.0818	9	0.1666	-	-
0.0909	10	0.0737	-	-
0.1	11	0.0997	-	-
0.1091	12	0.0795	-	-
0.1182	13	0.1071	-	-
0.1273	14	0.1224	-	-
0.1364	15	0.0499	-	-
0.1455	16	0.0806	-	-
0.1545	17	0.0353	-	-
0.1636	18	0.0542	-	-
0.1727	19	0.0412	-	-
0.1818	20	0.1375	-	-
0.1909	21	0.1124	-	-
0.2	22	0.0992	-	-
0.2091	23	0.0285	-	-
0.2182	24	0.0337	-	-
0.2273	25	0.0737	-	-
0.2364	26	0.2011	-	-
0.2455	27	0.0241	-	-
0.2545	28	0.1319	-	-
0.2636	29	0.0104	-	-
0.2727	30	0.0162	-	-
0.2818	31	0.3061	-	-
0.2909	32	0.0422	-	-
0.3	33	0.1893	-	-
0.3091	34	0.0207	-	-
0.3182	35	0.0744	-	-
0.3273	36	0.0246	-	-
0.3364	37	0.0079	-	-
0.3455	38	0.0256	-	-
0.3545	39	0.0224	-	-
0.3636	40	0.0151	-	-
0.3727	41	0.0738	-	-
0.3818	42	0.0239	-	-
0.3909	43	0.0169	-	-
0.4	44	0.0152	-	-
0.4091	45	0.0244	-	-
0.4182	46	0.1708	-	-
0.4273	47	0.0146	-	-
0.4364	48	0.1367	-	-
0.4455	49	0.049	-	-
0.4545	50	0.0211	-	-
0.4636	51	0.0135	-	-
0.4727	52	0.0668	-	-
0.4818	53	0.087	-	-
0.4909	54	0.0046	-	-
0.5	55	0.0032	-	-
0.5091	56	0.0133	-	-
0.5182	57	0.0109	-	-
0.5273	58	0.0396	-	-
0.5364	59	0.0291	-	-
0.5455	60	0.0299	-	-
0.5545	61	0.0134	-	-
0.5636	62	0.0135	-	-
0.5727	63	0.0049	-	-
0.5818	64	0.0199	-	-
0.5909	65	0.1533	-	-
0.6	66	0.3639	-	-
0.6091	67	0.0652	-	-
0.6182	68	0.0315	-	-
0.6273	69	0.0403	-	-
0.6364	70	0.011	-	-
0.6455	71	0.0265	-	-
0.6545	72	0.1146	-	-
0.6636	73	0.0932	-	-
0.6727	74	0.0234	-	-
0.6818	75	0.0581	-	-
0.6909	76	0.0132	-	-
0.7	77	0.1183	-	-
0.7091	78	0.0913	-	-
0.7182	79	0.0262	-	-
0.7273	80	0.0262	-	-
0.7364	81	0.0159	-	-
0.7455	82	0.0407	-	-
0.7545	83	0.0294	-	-
0.7636	84	0.0567	-	-
0.7727	85	0.0959	-	-
0.7818	86	0.033	-	-
0.7909	87	0.0234	-	-
0.8	88	0.0088	-	-
0.8091	89	0.0249	-	-
0.8182	90	0.0276	-	-
0.8273	91	0.0936	-	-
0.8364	92	0.0067	-	-
0.8455	93	0.0064	-	-
0.8545	94	0.0654	-	-
0.8636	95	0.0048	-	-
0.8727	96	0.0087	-	-
0.8818	97	0.0115	-	-
0.8909	98	0.0092	-	-
0.9	99	0.0514	-	-
0.9091	100	0.1856	-	-
0.9182	101	0.0364	-	-
0.9273	102	0.0455	-	-
0.9364	103	0.0057	-	-
0.9455	104	0.0038	-	-
0.9545	105	0.0209	-	-
0.9636	106	0.0247	-	-
0.9727	107	0.0735	-	-
0.9818	108	0.004	-	-
0.9909	109	0.0174	-	-
1.0	110	0.018	0.0282	0.7093
1.0091	111	0.0187	-	-
1.0182	112	0.0116	-	-
1.0273	113	0.0043	-	-
1.0364	114	0.0059	-	-
1.0455	115	0.0067	-	-
1.0545	116	0.0093	-	-
1.0636	117	0.0821	-	-
1.0727	118	0.0097	-	-
1.0818	119	0.0141	-	-
1.0909	120	0.0202	-	-
1.1	121	0.0034	-	-
1.1091	122	0.0025	-	-
1.1182	123	0.006	-	-
1.1273	124	0.004	-	-
1.1364	125	0.003	-	-
1.1455	126	0.0399	-	-
1.1545	127	0.0026	-	-
1.1636	128	0.0043	-	-
1.1727	129	0.1317	-	-
1.1818	130	0.0024	-	-
1.1909	131	0.0027	-	-
1.2	132	0.076	-	-
1.2091	133	0.0302	-	-
1.2182	134	0.0026	-	-
1.2273	135	0.1611	-	-
1.2364	136	0.0413	-	-
1.2455	137	0.0118	-	-
1.2545	138	0.0042	-	-
1.2636	139	0.0401	-	-
1.2727	140	0.0036	-	-
1.2818	141	0.0034	-	-
1.2909	142	0.0026	-	-
1.3	143	0.0044	-	-
1.3091	144	0.0024	-	-
1.3182	145	0.0036	-	-
1.3273	146	0.0242	-	-
1.3364	147	0.0015	-	-
1.3455	148	0.1008	-	-
1.3545	149	0.0057	-	-
1.3636	150	0.0062	-	-
1.3727	151	0.0048	-	-
1.3818	152	0.0026	-	-
1.3909	153	0.0045	-	-
1.4	154	0.0139	-	-
1.4091	155	0.0017	-	-
1.4182	156	0.0012	-	-
1.4273	157	0.0009	-	-
1.4364	158	0.006	-	-
1.4455	159	0.0618	-	-
1.4545	160	0.0889	-	-
1.4636	161	0.0034	-	-
1.4727	162	0.0184	-	-
1.4818	163	0.0035	-	-
1.4909	164	0.002	-	-
1.5	165	0.0115	-	-
1.5091	166	0.0008	-	-
1.5182	167	0.0113	-	-
1.5273	168	0.01	-	-
1.5364	169	0.0177	-	-
1.5455	170	0.0059	-	-
1.5545	171	0.0123	-	-
1.5636	172	0.0103	-	-
1.5727	173	0.008	-	-
1.5818	174	0.002	-	-
1.5909	175	0.0039	-	-
1.6	176	0.0174	-	-
1.6091	177	0.0191	-	-
1.6182	178	0.002	-	-
1.6273	179	0.0009	-	-
1.6364	180	0.0021	-	-
1.6455	181	0.0011	-	-
1.6545	182	0.0027	-	-
1.6636	183	0.0005	-	-
1.6727	184	0.0026	-	-
1.6818	185	0.0047	-	-
1.6909	186	0.0033	-	-
1.7	187	0.0402	-	-
1.7091	188	0.0128	-	-
1.7182	189	0.01	-	-
1.7273	190	0.0057	-	-
1.7364	191	0.0133	-	-
1.7455	192	0.0099	-	-
1.7545	193	0.1022	-	-
1.7636	194	0.0223	-	-
1.7727	195	0.0037	-	-
1.7818	196	0.0073	-	-
1.7909	197	0.0212	-	-
1.8	198	0.0231	-	-
1.8091	199	0.0016	-	-
1.8182	200	0.0017	-	-
1.8273	201	0.0035	-	-
1.8364	202	0.0165	-	-
1.8455	203	0.0131	-	-
1.8545	204	0.0032	-	-
1.8636	205	0.0075	-	-
1.8727	206	0.0438	-	-
1.8818	207	0.0022	-	-
1.8909	208	0.0501	-	-
1.9	209	0.0121	-	-
1.9091	210	0.0036	-	-
1.9182	211	0.0041	-	-
1.9273	212	0.0048	-	-
1.9364	213	0.0159	-	-
1.9455	214	0.0036	-	-
1.9545	215	0.0035	-	-
1.9636	216	0.004	-	-
1.9727	217	0.0039	-	-
1.9818	218	0.0177	-	-
1.9909	219	0.0042	-	-
2.0	220	0.0044	0.0230	0.7225
2.0091	221	0.0339	-	-
2.0182	222	0.0032	-	-
2.0273	223	0.0133	-	-
2.0364	224	0.0031	-	-
2.0455	225	0.0025	-	-
2.0545	226	0.0039	-	-
2.0636	227	0.0011	-	-
2.0727	228	0.0021	-	-
2.0818	229	0.0591	-	-
2.0909	230	0.0011	-	-
2.1	231	0.0008	-	-
2.1091	232	0.0014	-	-
2.1182	233	0.0057	-	-
2.1273	234	0.0044	-	-
2.1364	235	0.001	-	-
2.1455	236	0.0009	-	-
2.1545	237	0.0028	-	-
2.1636	238	0.0076	-	-
2.1727	239	0.0018	-	-
2.1818	240	0.0022	-	-
2.1909	241	0.0029	-	-
2.2	242	0.0004	-	-
2.2091	243	0.0025	-	-
2.2182	244	0.0013	-	-
2.2273	245	0.0487	-	-
2.2364	246	0.0016	-	-
2.2455	247	0.0023	-	-
2.2545	248	0.0038	-	-
2.2636	249	0.003	-	-
2.2727	250	0.0017	-	-
2.2818	251	0.0056	-	-
2.2909	252	0.0036	-	-
2.3	253	0.0016	-	-
2.3091	254	0.0021	-	-
2.3182	255	0.0019	-	-
2.3273	256	0.001	-	-
2.3364	257	0.0017	-	-
2.3455	258	0.0027	-	-
2.3545	259	0.0039	-	-
2.3636	260	0.0011	-	-
2.3727	261	0.0248	-	-
2.3818	262	0.0219	-	-
2.3909	263	0.0015	-	-
2.4	264	0.0009	-	-
2.4091	265	0.0013	-	-
2.4182	266	0.0049	-	-
2.4273	267	0.0073	-	-
2.4364	268	0.007	-	-
2.4455	269	0.0024	-	-
2.4545	270	0.0008	-	-
2.4636	271	0.001	-	-
2.4727	272	0.0016	-	-
2.4818	273	0.0007	-	-
2.4909	274	0.0091	-	-
2.5	275	0.0127	-	-
2.5091	276	0.0013	-	-
2.5182	277	0.001	-	-
2.5273	278	0.0006	-	-
2.5364	279	0.005	-	-
2.5455	280	0.0154	-	-
2.5545	281	0.0015	-	-
2.5636	282	0.0229	-	-
2.5727	283	0.0026	-	-
2.5818	284	0.0008	-	-
2.5909	285	0.0024	-	-
2.6	286	0.0012	-	-
2.6091	287	0.0748	-	-
2.6182	288	0.0086	-	-
2.6273	289	0.0013	-	-
2.6364	290	0.0089	-	-
2.6455	291	0.0011	-	-
2.6545	292	0.0096	-	-
2.6636	293	0.1416	-	-
2.6727	294	0.0005	-	-
2.6818	295	0.0021	-	-
2.6909	296	0.0014	-	-
2.7	297	0.0097	-	-
2.7091	298	0.0014	-	-
2.7182	299	0.0009	-	-
2.7273	300	0.0016	-	-
2.7364	301	0.0166	-	-
2.7455	302	0.0028	-	-
2.7545	303	0.0014	-	-
2.7636	304	0.0018	-	-
2.7727	305	0.0059	-	-
2.7818	306	0.0012	-	-
2.7909	307	0.0008	-	-
2.8	308	0.0007	-	-
2.8091	309	0.0038	-	-
2.8182	310	0.0012	-	-
2.8273	311	0.0091	-	-
2.8364	312	0.0111	-	-
2.8455	313	0.0016	-	-
2.8545	314	0.0089	-	-
2.8636	315	0.0071	-	-
2.8727	316	0.0012	-	-
2.8818	317	0.0251	-	-
2.8909	318	0.0017	-	-
2.9	319	0.0006	-	-
2.9091	320	0.0014	-	-
2.9182	321	0.0011	-	-
2.9273	322	0.0084	-	-
2.9364	323	0.0055	-	-
2.9455	324	0.0011	-	-
2.9545	325	0.0017	-	-
2.9636	326	0.0008	-	-
2.9727	327	0.0082	-	-
2.9818	328	0.0006	-	-
2.9909	329	0.0008	-	-
3.0	330	0.0022	0.0275	0.6950
3.0091	331	0.0007	-	-
3.0182	332	0.0012	-	-
3.0273	333	0.0007	-	-
3.0364	334	0.0038	-	-
3.0455	335	0.0006	-	-
3.0545	336	0.0012	-	-
3.0636	337	0.0873	-	-
3.0727	338	0.0022	-	-
3.0818	339	0.0004	-	-
3.0909	340	0.001	-	-
3.1	341	0.0002	-	-
3.1091	342	0.0069	-	-
3.1182	343	0.0009	-	-
3.1273	344	0.0101	-	-
3.1364	345	0.0022	-	-
3.1455	346	0.009	-	-
3.1545	347	0.0018	-	-
3.1636	348	0.0018	-	-
3.1727	349	0.0045	-	-
3.1818	350	0.029	-	-
3.1909	351	0.0036	-	-
3.2	352	0.0015	-	-
3.2091	353	0.0021	-	-
3.2182	354	0.0103	-	-
3.2273	355	0.0005	-	-
3.2364	356	0.0133	-	-
3.2455	357	0.0015	-	-
3.2545	358	0.001	-	-
3.2636	359	0.0024	-	-
3.2727	360	0.0052	-	-
3.2818	361	0.0032	-	-
3.2909	362	0.0024	-	-
3.3	363	0.0008	-	-
3.3091	364	0.0035	-	-
3.3182	365	0.0012	-	-
3.3273	366	0.0049	-	-
3.3364	367	0.0452	-	-
3.3455	368	0.0017	-	-
3.3545	369	0.0112	-	-
3.3636	370	0.0011	-	-
3.3727	371	0.0016	-	-
3.3818	372	0.0015	-	-
3.3909	373	0.004	-	-
3.4	374	0.0074	-	-
3.4091	375	0.0005	-	-
3.4182	376	0.0007	-	-
3.4273	377	0.0014	-	-
3.4364	378	0.0097	-	-
3.4455	379	0.0026	-	-
3.4545	380	0.0022	-	-
3.4636	381	0.001	-	-
3.4727	382	0.0004	-	-
3.4818	383	0.004	-	-
3.4909	384	0.0017	-	-
3.5	385	0.0014	-	-
3.5091	386	0.001	-	-
3.5182	387	0.0047	-	-
3.5273	388	0.0061	-	-
3.5364	389	0.0017	-	-
3.5455	390	0.0024	-	-
3.5545	391	0.0021	-	-
3.5636	392	0.0007	-	-
3.5727	393	0.0009	-	-
3.5818	394	0.0006	-	-
3.5909	395	0.0038	-	-
3.6	396	0.0006	-	-
3.6091	397	0.0011	-	-
3.6182	398	0.001	-	-
3.6273	399	0.0014	-	-
3.6364	400	0.0007	-	-
3.6455	401	0.0052	-	-
3.6545	402	0.0008	-	-
3.6636	403	0.0009	-	-
3.6727	404	0.0017	-	-
3.6818	405	0.0028	-	-
3.6909	406	0.0044	-	-
3.7	407	0.0009	-	-
3.7091	408	0.0134	-	-
3.7182	409	0.001	-	-
3.7273	410	0.0044	-	-
3.7364	411	0.0138	-	-
3.7455	412	0.0032	-	-
3.7545	413	0.0004	-	-
3.7636	414	0.0065	-	-
3.7727	415	0.0007	-	-
3.7818	416	0.0008	-	-
3.7909	417	0.0007	-	-
3.8	418	0.0018	-	-
3.8091	419	0.001	-	-
3.8182	420	0.0305	-	-
3.8273	421	0.001	-	-
3.8364	422	0.0011	-	-
3.8455	423	0.0004	-	-
3.8545	424	0.003	-	-
3.8636	425	0.002	-	-
3.8727	426	0.0018	-	-
3.8818	427	0.0968	-	-
3.8909	428	0.002	-	-
3.9	429	0.002	-	-
3.9091	430	0.0156	-	-
3.9182	431	0.0059	-	-
3.9273	432	0.001	-	-
3.9364	433	0.0153	-	-
3.9455	434	0.0013	-	-
3.9545	435	0.0003	-	-
3.9636	436	0.001	-	-
3.9727	437	0.0005	-	-
3.9818	438	0.0012	-	-
3.9909	439	0.0109	-	-
4.0	440	0.1597	0.0211	0.7235
4.0091	441	0.0027	-	-
4.0182	442	0.0007	-	-
4.0273	443	0.0089	-	-
4.0364	444	0.0007	-	-
4.0455	445	0.005	-	-
4.0545	446	0.0019	-	-
4.0636	447	0.0007	-	-
4.0727	448	0.0008	-	-
4.0818	449	0.002	-	-
4.0909	450	0.043	-	-
4.1	451	0.0273	-	-
4.1091	452	0.0009	-	-
4.1182	453	0.0011	-	-
4.1273	454	0.0007	-	-
4.1364	455	0.0062	-	-
4.1455	456	0.0004	-	-
4.1545	457	0.0008	-	-
4.1636	458	0.0128	-	-
4.1727	459	0.0012	-	-
4.1818	460	0.0013	-	-
4.1909	461	0.0009	-	-
4.2	462	0.0011	-	-
4.2091	463	0.0336	-	-
4.2182	464	0.0018	-	-
4.2273	465	0.0009	-	-
4.2364	466	0.0049	-	-
4.2455	467	0.0012	-	-
4.2545	468	0.001	-	-
4.2636	469	0.0024	-	-
4.2727	470	0.0063	-	-
4.2818	471	0.0008	-	-
4.2909	472	0.0793	-	-
4.3	473	0.0016	-	-
4.3091	474	0.0016	-	-
4.3182	475	0.0043	-	-
4.3273	476	0.036	-	-
4.3364	477	0.002	-	-
4.3455	478	0.0019	-	-
4.3545	479	0.0012	-	-
4.3636	480	0.0059	-	-
4.3727	481	0.0017	-	-
4.3818	482	0.0004	-	-
4.3909	483	0.0014	-	-
4.4	484	0.0143	-	-
4.4091	485	0.0014	-	-
4.4182	486	0.0009	-	-
4.4273	487	0.0027	-	-
4.4364	488	0.0017	-	-
4.4455	489	0.0007	-	-
4.4545	490	0.0008	-	-
4.4636	491	0.0008	-	-
4.4727	492	0.0014	-	-
4.4818	493	0.0011	-	-
4.4909	494	0.0013	-	-
4.5	495	0.0016	-	-
4.5091	496	0.001	-	-
4.5182	497	0.0008	-	-
4.5273	498	0.001	-	-
4.5364	499	0.0019	-	-
4.5455	500	0.0008	-	-

Framework Versions

• Python: 3.12.9
• Sentence Transformers: 4.1.0
• Transformers: 4.52.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.7.0
• Datasets: 3.6.0
• Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}